Scene Text Recognition On Wost

1:1 Accuracy

Résultats

Résultats de performance de divers modèles sur ce benchmark

		Paper Title
CLIP4STR-H (DFN-5B)	90.9	CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model
CLIP4STR-L (DataComp-1B)	90.6	CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model
CLIP4STR-L	88.8	CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model
CLIP4STR-B	87.0	CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model
CCD-ViT-Base	86.0	Self-supervised Character-to-Character Distillation for Text Recognition

0 of 5 row(s) selected.